© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 880
    Prev
    Next
    INDEX
    Explanations

    CSS or other code related to colors

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.69
     HasFactory
    -0.60
     oignons
    -0.52
     Rude
    -0.49
    ENODEV
    -0.48
     getItemId
    -0.48
    hoeddwyd
    -0.47
     GenerationType
    -0.47
    Rude
    -0.46
    __":
    -0.45
    POSITIVE LOGITS
     colors
    1.34
     color
    1.34
     yellow
    1.30
     colour
    1.23
     Colors
    1.22
     blue
    1.21
     colours
    1.21
     Color
    1.21
     black
    1.20
     white
    1.20
    Activations Density 0.936%

    No Known Activations